chengzeyi / ParaAttentionLinks
https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
☆365Updated last month
Alternatives and similar repositories for ParaAttention
Users that are interested in ParaAttention are comparing it to the libraries listed below
Sorting:
- Light Video Generation Inference Framework☆489Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆607Updated last week
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆375Updated 2 months ago
- Radial Attention Official Implementation☆485Updated 2 weeks ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆266Updated 2 weeks ago
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆31Updated 4 months ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆242Updated 7 months ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆205Updated 6 months ago
- Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x fast…☆274Updated 10 months ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,071Updated 2 months ago
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆412Updated 2 months ago
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆703Updated 8 months ago
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.☆688Updated last week
- The official code for "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆191Updated this week
- 🤗An Unified Cache Acceleration Toolbox for DiTs: Qwen-Image, Qwen-Image-Edit, FLUX.1, Wan2.1/2.2, etc.☆201Updated this week
- ☆284Updated 7 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆138Updated 2 months ago
- ☆214Updated this week
- [NeurIPS 2024] Boosting the performance of consistency models with PCM!☆489Updated 8 months ago
- Making Flux go brrr on GPUs.☆131Updated last month
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆170Updated 5 months ago
- ☆173Updated 7 months ago
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆377Updated last week
- A parallelism VAE avoids OOM for high resolution image generation☆73Updated 3 weeks ago
- T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!☆405Updated 6 months ago
- VGDFR: Diffuison-based Video Generation with Dynamic Frame Rate☆12Updated 3 months ago
- Faster generation with text-to-image diffusion models.☆225Updated last month
- An out-of-the-box inference acceleration engine for Diffusion and DiT models☆53Updated 5 months ago
- Enhance-A-Video: Better Generated Video for Free☆568Updated 5 months ago
- faster parallel inference of mochi-1 video generation model☆125Updated 6 months ago